On 04/09/2013 12:33 AM, Olivier Mauras wrote:
Hello,
I can't access the bug, what is the status ?
Interesting, wonder why they took it private. Perhaps that is a good
sign :). Unfortunately no comments yet.
On 2013-04-06 16:44, Orion Poplawski wrote:
On 04/05/2013 07:32 PM, Bill Maidment wrote:
After switching back to the older kernel, I can confirm that the swap
usage has returned to normal, even during the backup time 6am-8am.
(See attached graph) I'm wondering if this has anything to do with
NUMA, which sometimes prefers to use swap rather than memory that is
slightly slower than the currently used memory. I am using a single
Phenom II 955 processor (quad core) on an ASUS M4N68T motherboard and
SL6.4 upgraded from 6.3
Switching back fixed it for me too. Max swap usage reduced from 100% to
25%, all dumps completed on time. I suppose NUMA could be a factor,
this is a Xeon L5520 system. I haven't seen this large swap usage on my
other older hardware, although I only have the one machine writing
backups to local disk, remote machines send the backup via the network
to this host.
I've filedhttps://bugzilla.redhat.com/show_bug.cgi?id=949166
--
Orion Poplawski
Technical Manager 303-415-9701 x222
NWRA/CoRA Division FAX: 303-415-9702
3380 Mitchell Lane [email protected]
Boulder, CO 80301 http://www.cora.nwra.com
